Paper Group NANR 219
A «Portrait» Approach to Multichannel Discourse. TESLA: Task-wise Early Stopping and Loss Aggregation for Dynamic Neural Network Inference. Multi-encoder Transformer Network for Automatic Post-Editing. Correcting the Triplet Selection Bias for Triplet Loss. Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoi …
A «Portrait» Approach to Multichannel Discourse
| Title | A «Portrait» Approach to Multichannel Discourse |
| Authors | Andrej Kibrik, Olga Fedorova |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1300/ |
| https://www.aclweb.org/anthology/L18-1300 | |
| PWC | https://paperswithcode.com/paper/a-aportraita-approach-to-multichannel |
| Repo | |
| Framework | |
TESLA: Task-wise Early Stopping and Loss Aggregation for Dynamic Neural Network Inference
| Title | TESLA: Task-wise Early Stopping and Loss Aggregation for Dynamic Neural Network Inference |
| Authors | Chun-Min Chang, Chia-Ching Lin, Hung-Yi Ou Yang, Chin-Laung Lei, Kuan-Ta Chen |
| Abstract | For inference operations in deep neural networks on end devices, it is desirable to deploy a single pre-trained neural network model, which can dynamically scale across a computation range without comprising accuracy. To achieve this goal, Incomplete Dot Product (IDP) has been proposed to use only a subset of terms in dot products during forward propagation. However, there are some limitations, including noticeable performance degradation in operating regions with low computational costs, and essential performance limitations since IDP uses hand-crafted profile coefficients. In this paper, we extend IDP by proposing new training algorithms involving a single profile, which may be trainable or pre-determined, to significantly improve the overall performance, especially in operating regions with low computational costs. Specifically, we propose the Task-wise Early Stopping and Loss Aggregation (TESLA) algorithm, which is showed in our 3-layer multilayer perceptron on MNIST that outperforms the original IDP by 32% when only 10% of dot products terms are used and achieves 94.7% accuracy on average. By introducing trainable profile coefficients, TESLA further improves the accuracy to 95.5% without specifying coefficients in advance. Besides, TESLA is applied to the VGG-16 model, which achieves 80% accuracy using only 20% of dot product terms on CIFAR-10 and also keeps 60% accuracy using only 30% of dot product terms on CIFAR-100, but the original IDP performs like a random guess in these two datasets at such low computation costs. Finally, we visualize the learned representations at different dot product percentages by class activation map and show that, by applying TESLA, the learned representations can adapt over a wide range of operation regions. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1K6Tb-AZ |
| https://openreview.net/pdf?id=H1K6Tb-AZ | |
| PWC | https://paperswithcode.com/paper/tesla-task-wise-early-stopping-and-loss |
| Repo | |
| Framework | |
Multi-encoder Transformer Network for Automatic Post-Editing
| Title | Multi-encoder Transformer Network for Automatic Post-Editing |
| Authors | Jaehun Shin, Jong-Hyeok Lee |
| Abstract | This paper describes the POSTECH{'}s submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network. We modified the encoder-decoder attention to reflect the relation between the machine translation output, the source and the post-edited translation in APE problem. Experiments on WMT17 English-German APE data set show an improvement in both TER and BLEU score over the best result of WMT17 APE shared task. Our primary submission achieves -4.52 TER and +6.81 BLEU score on PBSMT task and -0.13 TER and +0.40 BLEU score for NMT task compare to the baseline. |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6470/ |
| https://www.aclweb.org/anthology/W18-6470 | |
| PWC | https://paperswithcode.com/paper/multi-encoder-transformer-network-for |
| Repo | |
| Framework | |
Correcting the Triplet Selection Bias for Triplet Loss
| Title | Correcting the Triplet Selection Bias for Triplet Loss |
| Authors | Baosheng Yu, Tongliang Liu, Mingming Gong, Changxing Ding, Dacheng Tao |
| Abstract | Triplet loss, popular for metric learning, has made a great success in many computer vision tasks, such as fine-grained image classification, image retrieval, and face recognition. Considering that the number of triplets grows cubically with the size of training data, triplet mining is thus indispensable for efficiently training with triplet loss. However, in practice, the training is usually very sensitive to the selected triplets, e.g., it almost does not converge with randomly selected triplets and selecting hardest triplets also leads to bad local minima. We argue that the bias in sampling of triplets degrades the performance of learning with triplet loss. In this paper, we propose a new variant of triplet loss, which tries to reduce the bias in triplet sampling by adaptively correcting the distribution shift on sampled triplets. We refer to this new triplet loss as adapted triplet loss. We conduct a number of experiments on MNIST and Fashion-MNIST for image classification, and on CARS196, CUB200-2011, and Stanford Online Products for image retrieval. The experimental results demonstrate the effectiveness of the proposed method. |
| Tasks | Face Recognition, Fine-Grained Image Classification, Image Classification, Image Retrieval, Metric Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Baosheng_Yu_Correcting_the_Triplet_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Baosheng_Yu_Correcting_the_Triplet_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/correcting-the-triplet-selection-bias-for |
| Repo | |
| Framework | |
Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift
| Title | Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift |
| Authors | Ajay Nagesh, Mihai Surdeanu |
| Abstract | We propose a novel approach to semi-supervised learning for information extraction that uses ladder networks (Rasmus et al., 2015). In particular, we focus on the task of named entity classification, defined as identifying the correct label (e.g., person or organization name) of an entity mention in a given context. Our approach is simple, efficient and has the benefit of being robust to semantic drift, a dominant problem in most semi-supervised learning systems. We empirically demonstrate the superior performance of our system compared to the state-of-the-art on two standard datasets for named entity classification. We obtain between 62{%} and 200{%} improvement over the state-of-art baseline on these two datasets. |
| Tasks | Denoising |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2057/ |
| https://www.aclweb.org/anthology/N18-2057 | |
| PWC | https://paperswithcode.com/paper/keep-your-bearings-lightly-supervised |
| Repo | |
| Framework | |
What we need to learn if we want to do and not just talk
| Title | What we need to learn if we want to do and not just talk |
| Authors | Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan |
| Abstract | In task-oriented dialog, agents need to generate both fluent natural language responses and correct external actions like database queries and updates. Our paper makes the first attempt at evaluating state of the art models on a large real world task with human users. We show that methods that achieve state of the art performance on synthetic datasets, perform poorly in real world dialog tasks. We propose a hybrid model, where nearest neighbor is used to generate fluent responses and Seq2Seq type models ensure dialogue coherency and generate accurate external actions. The hybrid model on the customer support data achieves a 78{%} relative improvement in fluency, and a 200{%} improvement in accuracy of external calls. |
| Tasks | Chatbot, Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-3004/ |
| https://www.aclweb.org/anthology/N18-3004 | |
| PWC | https://paperswithcode.com/paper/what-we-need-to-learn-if-we-want-to-do-and |
| Repo | |
| Framework | |
Revisiting Autofocus for Smartphone Cameras
| Title | Revisiting Autofocus for Smartphone Cameras |
| Authors | Abdullah Abuolaim, Abhijith Punnappurath, Michael S. Brown |
| Abstract | Autofocus (AF) on smartphones is the process of determining how to move a camera’s lens such that certain scene content is in focus. The underlying algorithms used by AF systems, such as contrast detection and phase differencing, are well established. However, determining a high-level objective regarding how to best focus a particular scene is less clear. This is evident in part by the fact that different smartphone cameras employ different AF criteria; for example, some attempt to keep items in the center in focus, others give priority to faces while others maximize the sharpness of the entire scene. The fact that different objectives exist raises the research question of whether there is a preferred objective. This becomes more interesting when AF is applied to videos of dynamic scenes. The work in this paper aims to revisit AF for smartphones within the context of temporal image data. As part of this effort, we describe the capture of a new 4D dataset that provides access to a full focal stack at each time point in a temporal sequence. Based on this dataset, we have developed a platform and associated application programming interface (API) that mimic real AF systems, restricting lens motion within the constraints of a dynamic environment and frame capture. Using our platform we evaluated several high-level focusing objectives and found interesting insight into what users prefer. We believe our new temporal focal stack dataset, AF platform, and initial user-study findings will be useful in advancing AF research. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Abdullah_Abuolaim_Revisiting_Autofocus_for_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Abdullah_Abuolaim_Revisiting_Autofocus_for_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-autofocus-for-smartphone-cameras |
| Repo | |
| Framework | |
On Misinformation Containment in Online Social Networks
| Title | On Misinformation Containment in Online Social Networks |
| Authors | Amo Tong, Ding-Zhu Du, Weili Wu |
| Abstract | The widespread online misinformation could cause public panic and serious economic damages. The misinformation containment problem aims at limiting the spread of misinformation in online social networks by launching competing campaigns. Motivated by realistic scenarios, we present the first analysis of the misinformation containment problem for the case when an arbitrary number of cascades are allowed. This paper makes four contributions. First, we provide a formal model for multi-cascade diffusion and introduce an important concept called as cascade priority. Second, we show that the misinformation containment problem cannot be approximated within a factor of $\Omega(2^{\log^{1-\epsilon}n^4})$ in polynomial time unless $NP \subseteq DTIME(n^{\polylog{n}})$. Third, we introduce several types of cascade priority that are frequently seen in real social networks. Finally, we design novel algorithms for solving the misinformation containment problem. The effectiveness of the proposed algorithm is supported by encouraging experimental results. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7317-on-misinformation-containment-in-online-social-networks |
| http://papers.nips.cc/paper/7317-on-misinformation-containment-in-online-social-networks.pdf | |
| PWC | https://paperswithcode.com/paper/on-misinformation-containment-in-online |
| Repo | |
| Framework | |
EventWiki: A Knowledge Base of Major Events
| Title | EventWiki: A Knowledge Base of Major Events |
| Authors | Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou |
| Abstract | |
| Tasks | Question Answering, Semantic Parsing |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1079/ |
| https://www.aclweb.org/anthology/L18-1079 | |
| PWC | https://paperswithcode.com/paper/eventwiki-a-knowledge-base-of-major-events |
| Repo | |
| Framework | |
Development of an Annotated Multimodal Dataset for the Investigation of Classification and Summarisation of Presentations using High-Level Paralinguistic Features
| Title | Development of an Annotated Multimodal Dataset for the Investigation of Classification and Summarisation of Presentations using High-Level Paralinguistic Features |
| Authors | Keith Curtis, Nick Campbell, Gareth Jones |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1340/ |
| https://www.aclweb.org/anthology/L18-1340 | |
| PWC | https://paperswithcode.com/paper/development-of-an-annotated-multimodal |
| Repo | |
| Framework | |
3C-GAN: AN CONDITION-CONTEXT-COMPOSITE GENERATIVE ADVERSARIAL NETWORKS FOR GENERATING IMAGES SEPARATELY
| Title | 3C-GAN: AN CONDITION-CONTEXT-COMPOSITE GENERATIVE ADVERSARIAL NETWORKS FOR GENERATING IMAGES SEPARATELY |
| Authors | Yeu-Chern Harn, Vladimir Jojic |
| Abstract | We present 3C-GAN: a novel multiple generators structures, that contains one conditional generator that generates a semantic part of an image conditional on its input label, and one context generator generates the rest of an image. Compared to original GAN model, this model has multiple generators and gives control over what its generators should generate. Unlike previous multi-generator models use a subsequent generation process, that one layer is generated given the previous layer, our model uses a process of generating different part of the images together. This way the model contains fewer parameters and the generation speed is faster. Specifically, the model leverages the label information to separate the object from the image correctly. Since the model conditional on the label information does not restrict to generate other parts of an image, we proposed a cost function that encourages the model to generate only the succinct part of an image in terms of label discrimination. We also found an exclusive prior on the mask of the model help separate the object. The experiments on MNIST, SVHN, and CelebA datasets show 3C-GAN can generate different objects with different generators simultaneously, according to the labels given to each generator. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HkCvZXbC- |
| https://openreview.net/pdf?id=HkCvZXbC- | |
| PWC | https://paperswithcode.com/paper/3c-gan-an-condition-context-composite |
| Repo | |
| Framework | |
Provably Correct Automatic Sub-Differentiation for Qualified Programs
| Title | Provably Correct Automatic Sub-Differentiation for Qualified Programs |
| Authors | Sham M. Kakade, Jason D. Lee |
| Abstract | The \emph{Cheap Gradient Principle}~\citep{Griewank:2008:EDP:1455489} — the computational cost of computing a $d$-dimensional vector of partial derivatives of a scalar function is nearly the same (often within a factor of $5$) as that of simply computing the scalar function itself — is of central importance in optimization; it allows us to quickly obtain (high-dimensional) gradients of scalar loss functions which are subsequently used in black box gradient-based optimization procedures. The current state of affairs is markedly different with regards to computing sub-derivatives: widely used ML libraries, including TensorFlow and PyTorch, do \emph{not} correctly compute (generalized) sub-derivatives even on simple differentiable examples. This work considers the question: is there a \emph{Cheap Sub-gradient Principle}? Our main result shows that, under certain restrictions on our library of non-smooth functions (standard in non-linear programming), provably correct generalized sub-derivatives can be computed at a computational cost that is within a (dimension-free) factor of $6$ of the cost of computing the scalar function itself. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7943-provably-correct-automatic-sub-differentiation-for-qualified-programs |
| http://papers.nips.cc/paper/7943-provably-correct-automatic-sub-differentiation-for-qualified-programs.pdf | |
| PWC | https://paperswithcode.com/paper/provably-correct-automatic-sub |
| Repo | |
| Framework | |
Medical Sentiment Analysis using Social Media: Towards building a Patient Assisted System
| Title | Medical Sentiment Analysis using Social Media: Towards building a Patient Assisted System |
| Authors | Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1442/ |
| https://www.aclweb.org/anthology/L18-1442 | |
| PWC | https://paperswithcode.com/paper/medical-sentiment-analysis-using-social-media |
| Repo | |
| Framework | |
Balanced and Deterministic Weight-sharing Helps Network Performance
| Title | Balanced and Deterministic Weight-sharing Helps Network Performance |
| Authors | Oscar Chang, Hod Lipson |
| Abstract | Weight-sharing plays a significant role in the success of many deep neural networks, by increasing memory efficiency and incorporating useful inductive priors about the problem into the network. But understanding how weight-sharing can be used effectively in general is a topic that has not been studied extensively. Chen et al. (2015) proposed HashedNets, which augments a multi-layer perceptron with a hash table, as a method for neural network compression. We generalize this method into a framework (ArbNets) that allows for efficient arbitrary weight-sharing, and use it to study the role of weight-sharing in neural networks. We show that common neural networks can be expressed as ArbNets with different hash functions. We also present two novel hash functions, the Dirichlet hash and the Neighborhood hash, and use them to demonstrate experimentally that balanced and deterministic weight-sharing helps with the performance of a neural network. |
| Tasks | Neural Network Compression |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJD8YjCpW |
| https://openreview.net/pdf?id=SJD8YjCpW | |
| PWC | https://paperswithcode.com/paper/balanced-and-deterministic-weight-sharing |
| Repo | |
| Framework | |
Collaborative Deep Reinforcement Learning for Multi-Object Tracking
| Title | Collaborative Deep Reinforcement Learning for Multi-Object Tracking |
| Authors | Liangliang Ren, Jiwen Lu, Zifeng Wang, Qi Tian, Jie Zhou |
| Abstract | In this paper, we propose a collaborative deep reinforcement learning (C-DRL) method for multi-object tracking. Most existing multi-object tracking methods employ the tracking-by-detection strategy which first detects objects in each frame and then associates them across different frames. However, the performance of these methods rely heavily on the detection results, which are usually unsatisfied in many real applications, especially in crowded scenes. To address this, we develop a deep prediction-decision network in our C-DRL, which simultaneously detects and predicts objects under a unified network via deep reinforcement learning. Specifically, we consider each object as an agent and track it via the prediction network, and seek the optimal tracked results by exploiting the collaborative interactions of different agents and environments via the decision network, so that the influences of occlusions and noisy detection results can be well alleviated. Experimental results on the challenging MOT15 and MOT16 benchmarks are presented to show the efficiency of our approach. |
| Tasks | Multi-Object Tracking, Object Tracking |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Liangliang_Ren_Collaborative_Deep_Reinforcement_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Liangliang_Ren_Collaborative_Deep_Reinforcement_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-deep-reinforcement-learning-for |
| Repo | |
| Framework | |
